Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    References :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ías
    0.42
    ذر
    0.40
    免费
    0.39
    Poz
    0.39
     térmica
    0.39
    íos
    0.38
     प्रदू
    0.38
    ід
    0.37
    無料
    0.36
    пла
    0.36
    POSITIVE LOGITS
    References
    0.48
     cit
    0.44
     References
    0.43
     citing
    0.43
    文中
    0.41
     references
    0.41
    ++]
    0.40
     cites
    0.40
     citations
    0.40
     numpy
    0.39
    Act Density 0.000%

    No Known Activations